1 files changed, 191 insertions, 98 deletions

diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index b13b8f93079d..5e1da088d8e1 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * INET		An implementation of the TCP/IP protocol suite for the LINUX
  *		operating system.  INET is implemented using the BSD Socket
@@ -7,42 +8,37 @@
  *
  * Authors:	Lotsa people, from code originally in tcp, generalised here
  *		by Arnaldo Carvalho de Melo <acme@mandriva.com>
- *
- *	This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
  */
 
 #include <linux/module.h>
 #include <linux/random.h>
 
 #include <net/addrconf.h>
+#include <net/hotdata.h>
 #include <net/inet_connection_sock.h>
 #include <net/inet_hashtables.h>
 #include <net/inet6_hashtables.h>
 #include <net/secure_seq.h>
 #include <net/ip.h>
 #include <net/sock_reuseport.h>
+#include <net/tcp.h>
 
 u32 inet6_ehashfn(const struct net *net,
 		  const struct in6_addr *laddr, const u16 lport,
 		  const struct in6_addr *faddr, const __be16 fport)
 {
-	static u32 inet6_ehash_secret __read_mostly;
-	static u32 ipv6_hash_secret __read_mostly;
-
 	u32 lhash, fhash;
 
 	net_get_random_once(&inet6_ehash_secret, sizeof(inet6_ehash_secret));
-	net_get_random_once(&ipv6_hash_secret, sizeof(ipv6_hash_secret));
+	net_get_random_once(&tcp_ipv6_hash_secret, sizeof(tcp_ipv6_hash_secret));
 
 	lhash = (__force u32)laddr->s6_addr32[3];
-	fhash = __ipv6_addr_jhash(faddr, ipv6_hash_secret);
+	fhash = __ipv6_addr_jhash(faddr, tcp_ipv6_hash_secret);
 
-	return __inet6_ehashfn(lhash, lport, fhash, fport,
-			       inet6_ehash_secret + net_hash_mix(net));
+	return lport + __inet6_ehashfn(lhash, 0, fhash, fport,
+				       inet6_ehash_secret + net_hash_mix(net));
 }
+EXPORT_SYMBOL_GPL(inet6_ehashfn);
 
 /*
  * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so
@@ -50,35 +46,34 @@ u32 inet6_ehashfn(const struct net *net,
  *
  * The sockhash lock must be held as a reader here.
  */
-struct sock *__inet6_lookup_established(struct net *net,
-					struct inet_hashinfo *hashinfo,
-					   const struct in6_addr *saddr,
-					   const __be16 sport,
-					   const struct in6_addr *daddr,
-					   const u16 hnum,
-					   const int dif)
+struct sock *__inet6_lookup_established(const struct net *net,
+					const struct in6_addr *saddr,
+					const __be16 sport,
+					const struct in6_addr *daddr,
+					const u16 hnum,
+					const int dif, const int sdif)
 {
-	struct sock *sk;
-	const struct hlist_nulls_node *node;
 	const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
-	/* Optimize here for direct hit, only listening connections can
-	 * have wildcards anyways.
-	 */
-	unsigned int hash = inet6_ehashfn(net, daddr, hnum, saddr, sport);
-	unsigned int slot = hash & hashinfo->ehash_mask;
-	struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
-
+	const struct hlist_nulls_node *node;
+	struct inet_ehash_bucket *head;
+	struct inet_hashinfo *hashinfo;
+	unsigned int hash, slot;
+	struct sock *sk;
 
+	hashinfo = net->ipv4.tcp_death_row.hashinfo;
+	hash = inet6_ehashfn(net, daddr, hnum, saddr, sport);
+	slot = hash & hashinfo->ehash_mask;
+	head = &hashinfo->ehash[slot];
 begin:
 	sk_nulls_for_each_rcu(sk, node, &head->chain) {
 		if (sk->sk_hash != hash)
 			continue;
-		if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif))
+		if (!inet6_match(net, sk, saddr, daddr, ports, dif, sdif))
 			continue;
 		if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
 			goto out;
 
-		if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports, dif))) {
+		if (unlikely(!inet6_match(net, sk, saddr, daddr, ports, dif, sdif))) {
 			sock_gen_put(sk);
 			goto begin;
 		}
@@ -93,75 +88,163 @@ found:
 }
 EXPORT_SYMBOL(__inet6_lookup_established);
 
-static inline int compute_score(struct sock *sk, struct net *net,
+static inline int compute_score(struct sock *sk, const struct net *net,
 				const unsigned short hnum,
 				const struct in6_addr *daddr,
-				const int dif, bool exact_dif)
+				const int dif, const int sdif)
 {
 	int score = -1;
 
 	if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum &&
 	    sk->sk_family == PF_INET6) {
+		if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
+			return -1;
 
-		score = 1;
-		if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
-			if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
-				return -1;
-			score++;
-		}
-		if (sk->sk_bound_dev_if || exact_dif) {
-			if (sk->sk_bound_dev_if != dif)
-				return -1;
-			score++;
-		}
-		if (sk->sk_incoming_cpu == raw_smp_processor_id())
+		if (!inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
+			return -1;
+
+		score =  sk->sk_bound_dev_if ? 2 : 1;
+		if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
 			score++;
 	}
 	return score;
 }
 
+/**
+ * inet6_lookup_reuseport() - execute reuseport logic on AF_INET6 socket if necessary.
+ * @net: network namespace.
+ * @sk: AF_INET6 socket, must be in TCP_LISTEN state for TCP or TCP_CLOSE for UDP.
+ * @skb: context for a potential SK_REUSEPORT program.
+ * @doff: header offset.
+ * @saddr: source address.
+ * @sport: source port.
+ * @daddr: destination address.
+ * @hnum: destination port in host byte order.
+ * @ehashfn: hash function used to generate the fallback hash.
+ *
+ * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to
+ *         the selected sock or an error.
+ */
+struct sock *inet6_lookup_reuseport(const struct net *net, struct sock *sk,
+				    struct sk_buff *skb, int doff,
+				    const struct in6_addr *saddr,
+				    __be16 sport,
+				    const struct in6_addr *daddr,
+				    unsigned short hnum,
+				    inet6_ehashfn_t *ehashfn)
+{
+	struct sock *reuse_sk = NULL;
+	u32 phash;
+
+	if (sk->sk_reuseport) {
+		phash = INDIRECT_CALL_INET(ehashfn, udp6_ehashfn, inet6_ehashfn,
+					   net, daddr, hnum, saddr, sport);
+		reuse_sk = reuseport_select_sock(sk, phash, skb, doff);
+	}
+	return reuse_sk;
+}
+EXPORT_SYMBOL_GPL(inet6_lookup_reuseport);
+
 /* called with rcu_read_lock() */
-struct sock *inet6_lookup_listener(struct net *net,
-		struct inet_hashinfo *hashinfo,
+static struct sock *inet6_lhash2_lookup(const struct net *net,
+		struct inet_listen_hashbucket *ilb2,
 		struct sk_buff *skb, int doff,
 		const struct in6_addr *saddr,
 		const __be16 sport, const struct in6_addr *daddr,
-		const unsigned short hnum, const int dif)
+		const unsigned short hnum, const int dif, const int sdif)
 {
-	unsigned int hash = inet_lhashfn(net, hnum);
-	struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
-	int score, hiscore = 0, matches = 0, reuseport = 0;
-	bool exact_dif = inet6_exact_dif_match(net, skb);
 	struct sock *sk, *result = NULL;
-	u32 phash = 0;
+	struct hlist_nulls_node *node;
+	int score, hiscore = 0;
 
-	sk_for_each(sk, &ilb->head) {
-		score = compute_score(sk, net, hnum, daddr, dif, exact_dif);
+	sk_nulls_for_each_rcu(sk, node, &ilb2->nulls_head) {
+		score = compute_score(sk, net, hnum, daddr, dif, sdif);
 		if (score > hiscore) {
-			reuseport = sk->sk_reuseport;
-			if (reuseport) {
-				phash = inet6_ehashfn(net, daddr, hnum,
-						      saddr, sport);
-				result = reuseport_select_sock(sk, phash,
-							       skb, doff);
-				if (result)
-					return result;
-				matches = 1;
-			}
+			result = inet6_lookup_reuseport(net, sk, skb, doff,
+							saddr, sport, daddr, hnum, inet6_ehashfn);
+			if (result)
+				return result;
+
 			result = sk;
 			hiscore = score;
-		} else if (score == hiscore && reuseport) {
-			matches++;
-			if (reciprocal_scale(phash, matches) == 0)
-				result = sk;
-			phash = next_pseudo_random32(phash);
 		}
 	}
+
+	return result;
+}
+
+struct sock *inet6_lookup_run_sk_lookup(const struct net *net,
+					int protocol,
+					struct sk_buff *skb, int doff,
+					const struct in6_addr *saddr,
+					const __be16 sport,
+					const struct in6_addr *daddr,
+					const u16 hnum, const int dif,
+					inet6_ehashfn_t *ehashfn)
+{
+	struct sock *sk, *reuse_sk;
+	bool no_reuseport;
+
+	no_reuseport = bpf_sk_lookup_run_v6(net, protocol, saddr, sport,
+					    daddr, hnum, dif, &sk);
+	if (no_reuseport || IS_ERR_OR_NULL(sk))
+		return sk;
+
+	reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff,
+					  saddr, sport, daddr, hnum, ehashfn);
+	if (reuse_sk)
+		sk = reuse_sk;
+	return sk;
+}
+EXPORT_SYMBOL_GPL(inet6_lookup_run_sk_lookup);
+
+struct sock *inet6_lookup_listener(const struct net *net,
+				   struct sk_buff *skb, int doff,
+				   const struct in6_addr *saddr,
+				   const __be16 sport,
+				   const struct in6_addr *daddr,
+				   const unsigned short hnum,
+				   const int dif, const int sdif)
+{
+	struct inet_listen_hashbucket *ilb2;
+	struct inet_hashinfo *hashinfo;
+	struct sock *result = NULL;
+	unsigned int hash2;
+
+	/* Lookup redirect from BPF */
+	if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
+		result = inet6_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff,
+						    saddr, sport, daddr, hnum, dif,
+						    inet6_ehashfn);
+		if (result)
+			goto done;
+	}
+
+	hashinfo = net->ipv4.tcp_death_row.hashinfo;
+	hash2 = ipv6_portaddr_hash(net, daddr, hnum);
+	ilb2 = inet_lhash2_bucket(hashinfo, hash2);
+
+	result = inet6_lhash2_lookup(net, ilb2, skb, doff,
+				     saddr, sport, daddr, hnum,
+				     dif, sdif);
+	if (result)
+		goto done;
+
+	/* Lookup lhash2 with in6addr_any */
+	hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
+	ilb2 = inet_lhash2_bucket(hashinfo, hash2);
+
+	result = inet6_lhash2_lookup(net, ilb2, skb, doff,
+				     saddr, sport, &in6addr_any, hnum,
+				     dif, sdif);
+done:
+	if (IS_ERR(result))
+		return NULL;
 	return result;
 }
 EXPORT_SYMBOL_GPL(inet6_lookup_listener);
 
-struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
+struct sock *inet6_lookup(const struct net *net,
 			  struct sk_buff *skb, int doff,
 			  const struct in6_addr *saddr, const __be16 sport,
 			  const struct in6_addr *daddr, const __be16 dport,
@@ -170,8 +253,8 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
 	struct sock *sk;
 	bool refcounted;
 
-	sk = __inet6_lookup(net, hashinfo, skb, doff, saddr, sport, daddr,
-			    ntohs(dport), dif, &refcounted);
+	sk = __inet6_lookup(net, skb, doff, saddr, sport, daddr,
+			    ntohs(dport), dif, 0, &refcounted);
 	if (sk && !refcounted && !refcount_inc_not_zero(&sk->sk_refcnt))
 		sk = NULL;
 	return sk;
@@ -180,33 +263,49 @@ EXPORT_SYMBOL_GPL(inet6_lookup);
 
 static int __inet6_check_established(struct inet_timewait_death_row *death_row,
 				     struct sock *sk, const __u16 lport,
-				     struct inet_timewait_sock **twp)
+				     struct inet_timewait_sock **twp,
+				     bool rcu_lookup,
+				     u32 hash)
 {
 	struct inet_hashinfo *hinfo = death_row->hashinfo;
 	struct inet_sock *inet = inet_sk(sk);
 	const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr;
 	const struct in6_addr *saddr = &sk->sk_v6_daddr;
 	const int dif = sk->sk_bound_dev_if;
-	const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
 	struct net *net = sock_net(sk);
-	const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr,
-						inet->inet_dport);
+	const int sdif = l3mdev_master_ifindex_by_index(net, dif);
+	const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
 	struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
-	spinlock_t *lock = inet_ehash_lockp(hinfo, hash);
-	struct sock *sk2;
-	const struct hlist_nulls_node *node;
 	struct inet_timewait_sock *tw = NULL;
+	const struct hlist_nulls_node *node;
+	struct sock *sk2;
+	spinlock_t *lock;
+
+	if (rcu_lookup) {
+		sk_nulls_for_each(sk2, node, &head->chain) {
+			if (sk2->sk_hash != hash ||
+			    !inet6_match(net, sk2, saddr, daddr,
+					 ports, dif, sdif))
+				continue;
+			if (sk2->sk_state == TCP_TIME_WAIT)
+				break;
+			return -EADDRNOTAVAIL;
+		}
+		return 0;
+	}
 
+	lock = inet_ehash_lockp(hinfo, hash);
 	spin_lock(lock);
 
 	sk_nulls_for_each(sk2, node, &head->chain) {
 		if (sk2->sk_hash != hash)
 			continue;
 
-		if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports, dif))) {
+		if (likely(inet6_match(net, sk2, saddr, daddr, ports,
+				       dif, sdif))) {
 			if (sk2->sk_state == TCP_TIME_WAIT) {
 				tw = inet_twsk(sk2);
-				if (twsk_unique(sk, sk2, twp))
+				if (tcp_twsk_unique(sk, sk2, twp))
 					break;
 			}
 			goto not_unique;
@@ -241,7 +340,7 @@ not_unique:
 	return -EADDRNOTAVAIL;
 }
 
-static u32 inet6_sk_port_offset(const struct sock *sk)
+static u64 inet6_sk_port_offset(const struct sock *sk)
 {
 	const struct inet_sock *inet = inet_sk(sk);
 
@@ -253,25 +352,19 @@ static u32 inet6_sk_port_offset(const struct sock *sk)
 int inet6_hash_connect(struct inet_timewait_death_row *death_row,
 		       struct sock *sk)
 {
-	u32 port_offset = 0;
+	const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr;
+	const struct in6_addr *saddr = &sk->sk_v6_daddr;
+	const struct inet_sock *inet = inet_sk(sk);
+	const struct net *net = sock_net(sk);
+	u64 port_offset = 0;
+	u32 hash_port0;
 
 	if (!inet_sk(sk)->inet_num)
 		port_offset = inet6_sk_port_offset(sk);
-	return __inet_hash_connect(death_row, sk, port_offset,
-				   __inet6_check_established);
-}
-EXPORT_SYMBOL_GPL(inet6_hash_connect);
-
-int inet6_hash(struct sock *sk)
-{
-	int err = 0;
 
-	if (sk->sk_state != TCP_CLOSE) {
-		local_bh_disable();
-		err = __inet_hash(sk, NULL);
-		local_bh_enable();
-	}
+	hash_port0 = inet6_ehashfn(net, daddr, 0, saddr, inet->inet_dport);
 
-	return err;
+	return __inet_hash_connect(death_row, sk, port_offset, hash_port0,
+				   __inet6_check_established);
 }
-EXPORT_SYMBOL_GPL(inet6_hash);
+EXPORT_SYMBOL_GPL(inet6_hash_connect);